active_storage_dedup 1.0.0.alpha → 1.0.0.beta

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a4f96450774fa2234c8f821d1444e709da77e1ddc506c5f2df6a303fad7576a4
-  data.tar.gz: a50c1171305466705117062c7cafaafac2433e73f6e3c3fdee7115f4268bdeff
+  metadata.gz: fcef2e3f799ca998bca328d8324f3e5038adf52508c73b61fa20ce7e6a4a9a30
+  data.tar.gz: ce928b0477db7dbd8360b15544e5cb8935ad177340f01685f5d06323599ab820
 SHA512:
-  metadata.gz: f00a16a468856689d0d6d9ad111c84b4377b6d66fbefda0f8505aa494116b2054c02c1c3caf1fb16db28ddfc28285313ab76844fe48ec72743fe8af9833cdf3a
-  data.tar.gz: 81bbc60a6bb8df0f1e8b4fbc0921fb98242a41a47aeb69d7207f4521712a1e79377c0f5fca8466a4b75d5aba7fbf6ecee4f14eaa411ac4b975d95b87713dbfc6
+  metadata.gz: 3af226e7307b32aead229012fcbf657bc9ddc2ce56167cb30e07100440582a084d9449ed749d9626874eadfdb60987bc89bfacffcb3252b35465249b703bb06f
+  data.tar.gz: b55a9314af3dfa0102f14dce01791af79a751f77a2fc2a296a77a9331a70e939196fb60a7a6b0441b10c207db75e4ebe5d3212004f9a1320854acfc95233d404

data/.rubocop.yml

@@ -1,5 +1,38 @@
 AllCops:
-  TargetRubyVersion: 3.1
+  TargetRubyVersion: 2.7
+
+Metrics/BlockLength:
+  Enabled: false
+
+Metrics/MethodLength:
+  Enabled: false
+
+Metrics/ClassLength:
+  Enabled: false
+
+Metrics/ModuleLength:
+  Enabled: false
+
+Metrics/ParameterLists:
+  Enabled: false
+
+Metrics/AbcSize:
+  Enabled: false
+
+Metrics/CyclomaticComplexity:
+  Enabled: false
+
+Metrics/PerceivedComplexity:
+  Enabled: false
+
+Layout/LineLength:
+  Enabled: false
+
+Naming/VariableNumber:
+  Enabled: false
+
+Naming/MethodParameterName:
+  Enabled: false
 
 Style/StringLiterals:
   EnforcedStyle: double_quotes

data/CHANGELOG.md

@@ -1,5 +1,14 @@
 ## [Unreleased]
 
+## [1.0.0.beta] - 2025-12-01
+
+- Enforce minimum support of Rails 7.2 and Ruby 3.1+ (`22910a5`)
+- Limit compatibility to officially supported Rails/Ruby versions (`e8c1391`)
+- Default the test run to specs only for faster feedback (`398b015`)
+- Expand CI matrix to cover all current Rails and Ruby releases (`16d90c9`)
+- Polish specs and linting (`716c0ff`, `7f1c556`)
+- Link the sample test application in docs (`62fcc33`)
+
 ## [1.0.0.alpha] - 2025-11-23
 
 - Initial release

data/Rakefile

@@ -9,4 +9,4 @@ require "rubocop/rake_task"
 
 RuboCop::RakeTask.new
 
-task default: %i[spec rubocop]
+task default: %i[spec]

data/lib/active_storage_dedup/attachment_options.rb

@@ -7,7 +7,7 @@ module ActiveStorageDedup
       ActiveStorageDedup.register_attachment(self.name, name, deduplicate: deduplicate)
 
       super(name, dependent: dependent, service: service,
-            strict_loading: strict_loading, **options)
+                  strict_loading: strict_loading, **options)
     end
 
     def has_many_attached(name, dependent: :purge_later, service: nil,
@@ -15,7 +15,7 @@ module ActiveStorageDedup
       ActiveStorageDedup.register_attachment(self.name, name, deduplicate: deduplicate)
 
       super(name, dependent: dependent, service: service,
-            strict_loading: strict_loading, **options)
+                  strict_loading: strict_loading, **options)
     end
   end
 end

data/lib/active_storage_dedup/blob_deduplication.rb

@@ -30,7 +30,7 @@ module ActiveStorageDedup
           actual_service_name = blob.service_name || service.name
           Rails.logger.debug "[ActiveStorageDedup] Checking for duplicates: checksum=#{blob.checksum[0..12]}..., service=#{actual_service_name}"
 
-          if existing_blob = find_by(checksum: blob.checksum, service_name: actual_service_name)
+          if (existing_blob = find_by(checksum: blob.checksum, service_name: actual_service_name))
             Rails.logger.info "[ActiveStorageDedup] ✓ Reusing existing blob #{existing_blob.id} (checksum: #{blob.checksum[0..12]}..., service: #{actual_service_name})"
             return existing_blob
           end
@@ -43,7 +43,7 @@ module ActiveStorageDedup
       end
 
       # HOOK 2: Direct uploads to cloud storage
-      def create_before_direct_upload!(key: nil, filename:, byte_size:, checksum:,
+      def create_before_direct_upload!(filename:, byte_size:, checksum:, key: nil,
                                        content_type: nil, metadata: nil,
                                        service_name: nil,
                                        __dedup_record: nil, __dedup_attachment_name: nil, **options)
@@ -69,7 +69,7 @@ module ActiveStorageDedup
         Rails.logger.debug "[ActiveStorageDedup] Checking for duplicates: checksum=#{checksum[0..12]}..., service=#{actual_service_name}"
 
         # Check for existing blob
-        if existing_blob = find_by(checksum: checksum, service_name: actual_service_name)
+        if (existing_blob = find_by(checksum: checksum, service_name: actual_service_name))
           Rails.logger.info "[ActiveStorageDedup] ✓ Reusing existing blob #{existing_blob.id} for direct upload (checksum: #{checksum[0..12]}..., service: #{actual_service_name})"
           return existing_blob
         end
@@ -86,7 +86,7 @@ module ActiveStorageDedup
       end
 
       # HOOK 3: Fallback for programmatic attach (record.file.attach(io: ...))
-      def create_after_unfurling!(key: nil, io:, filename:, content_type: nil,
+      def create_after_unfurling!(io:, filename:, key: nil, content_type: nil,
                                   metadata: nil, service_name: nil, identify: true,
                                   __dedup_record: nil, __dedup_attachment_name: nil, **options)
         Rails.logger.debug "[ActiveStorageDedup] create_after_unfurling! called for #{filename}"

data/lib/active_storage_dedup/deduplication_job.rb

@@ -23,10 +23,10 @@ module ActiveStorageDedup
 
       # Find all checksum+service combinations that have duplicates
       duplicate_groups = ActiveStorage::Blob
-        .select(:checksum, :service_name)
-        .group(:checksum, :service_name)
-        .having('COUNT(*) > 1')
-        .count
+                         .select(:checksum, :service_name)
+                         .group(:checksum, :service_name)
+                         .having("COUNT(*) > 1")
+                         .count
 
       if duplicate_groups.empty?
         Rails.logger.info "[ActiveStorageDedup] ✓ No duplicate blobs found - database is clean!"
@@ -36,7 +36,7 @@ module ActiveStorageDedup
       Rails.logger.info "[ActiveStorageDedup] Found #{duplicate_groups.size} group(s) with duplicates"
 
       total_merged = 0
-      duplicate_groups.each do |(checksum, service_name), count|
+      duplicate_groups.each_key do |(checksum, service_name)|
         merged = process_duplicate_group(checksum, service_name)
         total_merged += merged
       end
@@ -51,9 +51,9 @@ module ActiveStorageDedup
 
       # Find all blobs with same checksum and service
       duplicate_blobs = ActiveStorage::Blob
-        .where(checksum: checksum, service_name: service_name)
-        .order(:created_at)
-        .to_a
+                        .where(checksum: checksum, service_name: service_name)
+                        .order(:created_at)
+                        .to_a
 
       Rails.logger.debug "[ActiveStorageDedup] Found #{duplicate_blobs.size} blob(s) with checksum #{checksum[0..12]}..."
 
@@ -91,7 +91,7 @@ module ActiveStorageDedup
       Rails.logger.debug "[ActiveStorageDedup] Deleted duplicate blob #{duplicate.id} record"
 
       Rails.logger.info "[ActiveStorageDedup] ✓ Merged blob #{duplicate.id} (#{attachment_count} attachment(s)) into #{keeper.id}"
-    rescue => e
+    rescue StandardError => e
       Rails.logger.error "[ActiveStorageDedup] ✗ Error merging blob #{duplicate.id}: #{e.class.name} - #{e.message}"
       Rails.logger.debug "[ActiveStorageDedup] Error backtrace: #{e.backtrace.first(5).join("\n")}"
       # Don't raise - allow job to complete for other duplicates

data/lib/active_storage_dedup/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ActiveStorageDedup
-  VERSION = "1.0.0.alpha"
+  VERSION = "1.0.0.beta"
 end

data/lib/tasks/active_storage_dedup.rake

@@ -7,10 +7,10 @@ namespace :active_storage_dedup do
 
     # Group blobs by checksum and service_name, find groups with duplicates
     duplicate_groups = ActiveStorage::Blob
-      .select("checksum, service_name, COUNT(*) as blob_count")
-      .group(:checksum, :service_name)
-      .having("COUNT(*) > 1")
-      .order("blob_count DESC")
+                       .select("checksum, service_name, COUNT(*) as blob_count")
+                       .group(:checksum, :service_name)
+                       .having("COUNT(*) > 1")
+                       .order("blob_count DESC")
 
     if duplicate_groups.empty?
       puts "No duplicate blobs found!"
@@ -22,8 +22,8 @@ namespace :active_storage_dedup do
 
     duplicate_groups.each do |group|
       blobs = ActiveStorage::Blob
-        .where(checksum: group.checksum, service_name: group.service_name)
-        .order(:created_at)
+              .where(checksum: group.checksum, service_name: group.service_name)
+              .order(:created_at)
 
       keeper = blobs.first
       duplicates = blobs[1..]
@@ -37,7 +37,7 @@ namespace :active_storage_dedup do
       puts "Filename: #{keeper.filename}"
       puts "Total blobs: #{blobs.count}"
       puts "Keeper blob ID: #{keeper.id} (#{keeper.attachments.count} attachments)"
-      puts "Duplicate blob IDs: #{duplicates.map(&:id).join(', ')}"
+      puts "Duplicate blob IDs: #{duplicates.map(&:id).join(", ")}"
       puts "Total attachments across duplicates: #{duplicates.sum { |b| b.attachments.count }}"
       puts "Wasted storage: #{format_bytes(wasted_bytes)}"
       puts "-" * 80
@@ -78,9 +78,7 @@ namespace :active_storage_dedup do
         updated += 1
       end
 
-      if (index + 1) % 100 == 0
-        puts "Processed #{index + 1}/#{total_blobs} blobs..."
-      end
+      puts "Processed #{index + 1}/#{total_blobs} blobs..." if ((index + 1) % 100).zero?
     end
 
     puts "\nBackfill complete!"
@@ -92,7 +90,7 @@ namespace :active_storage_dedup do
   def format_bytes(bytes)
     return "0 B" if bytes.zero?
 
-    units = ["B", "KB", "MB", "GB", "TB"]
+    units = %w[B KB MB GB TB]
     exp = (Math.log(bytes) / Math.log(1024)).floor
     exp = [exp, units.length - 1].min
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: active_storage_dedup
 version: !ruby/object:Gem::Version
-  version: 1.0.0.alpha
+  version: 1.0.0.beta
 platform: ruby
 authors:
 - coderhs
@@ -10,63 +10,63 @@ cert_chain: []
 date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: rails
+  name: activestorage
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 6.0.0
+        version: 7.2.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 6.0.0
+        version: 7.2.0
 - !ruby/object:Gem::Dependency
-  name: activestorage
+  name: rails
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 6.0.0
+        version: 7.2.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 6.0.0
+        version: 7.2.0
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: combustion
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '1.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '1.3'
 - !ruby/object:Gem::Dependency
-  name: rspec-rails
+  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
-  name: sqlite3
+  name: rspec-rails
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -94,19 +94,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: combustion
+  name: sqlite3
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: '0'
 description: Prevents duplicate file uploads in Active Storage by reusing existing
   blobs with matching checksums and service names
 email:
@@ -151,7 +151,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.7.0
+      version: 3.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="